simulate.model {ggdmc}

Simulate response time data

Description

Simulate response time data either for one subject or multiple subjects. The simulation is based on a model object. For one subject, one must supply a true parameter vector to the ps argument.

Usage

## S3 method for class 'model'
simulate(object, nsim = NA, seed = NULL, nsub = NA,
  prior = NA, ps = NA, ...)

Arguments

object

a model object.

nsim

number of trials / responses. n can be a single number for a balanced design or a matrix for an unbalanced design, where rows are subjects and columns are design cells. If the matrix has one row then all subjects have the same n in each cell, if it has one column then all cells have the same n; Otherwise each entry specifies the n for a particular subject x design cell combination.

seed

a user specified random seed.

nsub

number of subjects

prior

a prior object

ps

a true parameter vector or matrix.

...

additional optional arguments.

Details

For multiple subjects, one can enter a matrix (or a row vector) as true parameters. Each row is to generate data separately for a subject. This is the fixed-effect model. To generate data based on a random-effect model, one must supply a prior object. In this case, ps argument is unused. Note in some cases, a random-effect model may fail to draw data from the model, because true parameters are randomly drawn from a prior object. This would happen sometimes in diffusion model, because certain parameter combinations are considered invalid.

ps can be a row vector, in which case each subject has identical parameters. It can also be a matrix with one row per subject, in which case it must have ns rows. The true values will be saved as parameters attribute in the output object.

Value

a data frame